diff options
| -rw-r--r-- | arch/riscv/kernel/unaligned_access_speed.c | 187 |
1 files changed, 121 insertions, 66 deletions
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index d9d4ca1fadc7..18e334549544 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -24,8 +24,12 @@ DEFINE_PER_CPU(long, misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; DEFINE_PER_CPU(long, vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; -#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS +static long unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; +static long unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; + static cpumask_t fast_misaligned_access; + +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS static int check_unaligned_access(void *param) { int cpu = smp_processor_id(); @@ -130,6 +134,50 @@ static void __init check_unaligned_access_nonboot_cpu(void *param) check_unaligned_access(pages[cpu]); } +/* Measure unaligned access speed on all CPUs present at boot in parallel. */ +static void __init check_unaligned_access_speed_all_cpus(void) +{ + unsigned int cpu; + unsigned int cpu_count = num_possible_cpus(); + struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL); + + if (!bufs) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return; + } + + /* + * Allocate separate buffers for each CPU so there's no fighting over + * cache lines. + */ + for_each_cpu(cpu, cpu_online_mask) { + bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!bufs[cpu]) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + goto out; + } + } + + /* Check everybody except 0, who stays behind to tend jiffies. */ + on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1); + + /* Check core 0. */ + smp_call_on_cpu(0, check_unaligned_access, bufs[0], true); + +out: + for_each_cpu(cpu, cpu_online_mask) { + if (bufs[cpu]) + __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER); + } + + kfree(bufs); +} +#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */ +static void __init check_unaligned_access_speed_all_cpus(void) +{ +} +#endif + DEFINE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key); static void modify_unaligned_access_branches(cpumask_t *mask, int weight) @@ -188,21 +236,29 @@ arch_initcall_sync(lock_and_set_unaligned_access_static_branch); static int riscv_online_cpu(unsigned int cpu) { - static struct page *buf; - /* We are already set since the last check */ - if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + goto exit; + } else if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param; goto exit; - - check_unaligned_access_emulated(NULL); - buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); - if (!buf) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - return -ENOMEM; } - check_unaligned_access(buf); - __free_pages(buf, MISALIGNED_BUFFER_ORDER); +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS + { + static struct page *buf; + + check_unaligned_access_emulated(NULL); + buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!buf) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return -ENOMEM; + } + + check_unaligned_access(buf); + __free_pages(buf, MISALIGNED_BUFFER_ORDER); + } +#endif exit: set_unaligned_access_static_branches(); @@ -217,50 +273,6 @@ static int riscv_offline_cpu(unsigned int cpu) return 0; } -/* Measure unaligned access speed on all CPUs present at boot in parallel. */ -static void __init check_unaligned_access_speed_all_cpus(void) -{ - unsigned int cpu; - unsigned int cpu_count = num_possible_cpus(); - struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL); - - if (!bufs) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - return; - } - - /* - * Allocate separate buffers for each CPU so there's no fighting over - * cache lines. - */ - for_each_cpu(cpu, cpu_online_mask) { - bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); - if (!bufs[cpu]) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - goto out; - } - } - - /* Check everybody except 0, who stays behind to tend jiffies. */ - on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1); - - /* Check core 0. */ - smp_call_on_cpu(0, check_unaligned_access, bufs[0], true); - -out: - for_each_cpu(cpu, cpu_online_mask) { - if (bufs[cpu]) - __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER); - } - - kfree(bufs); -} -#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */ -static void __init check_unaligned_access_speed_all_cpus(void) -{ -} -#endif - #ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS static void check_vector_unaligned_access(struct work_struct *work __always_unused) { @@ -372,8 +384,8 @@ static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __alway static int riscv_online_cpu_vec(unsigned int cpu) { - if (!has_vector()) { - per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; return 0; } @@ -388,30 +400,73 @@ static int riscv_online_cpu_vec(unsigned int cpu) return 0; } +static const char * const speed_str[] __initconst = { NULL, NULL, "slow", "fast", "unsupported" }; + +static int __init set_unaligned_scalar_speed_param(char *str) +{ + if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_FAST])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED; + else + return -EINVAL; + + return 1; +} +__setup("unaligned_scalar_speed=", set_unaligned_scalar_speed_param); + +static int __init set_unaligned_vector_speed_param(char *str) +{ + if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_FAST])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + else + return -EINVAL; + + return 1; +} +__setup("unaligned_vector_speed=", set_unaligned_vector_speed_param); + static int __init check_unaligned_access_all_cpus(void) { int cpu; - if (!check_unaligned_access_emulated_all_cpus()) + if (unaligned_scalar_speed_param == RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN && + !check_unaligned_access_emulated_all_cpus()) { check_unaligned_access_speed_all_cpus(); - - if (!has_vector()) { + } else { + pr_info("scalar unaligned access speed set to '%s' by command line\n", + speed_str[unaligned_scalar_speed_param]); for_each_online_cpu(cpu) - per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; - } else if (!check_vector_unaligned_access_emulated_all_cpus() && - IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { + per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param; + } + + if (!has_vector()) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + + if (unaligned_vector_speed_param == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN && + !check_vector_unaligned_access_emulated_all_cpus() && + IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { kthread_run(vec_check_unaligned_access_speed_all_cpus, NULL, "vec_check_unaligned_access_speed_all_cpus"); + } else { + pr_info("vector unaligned access speed set to '%s' by command line\n", + speed_str[unaligned_vector_speed_param]); + for_each_online_cpu(cpu) + per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; } /* * Setup hotplug callbacks for any new CPUs that come online or go * offline. */ -#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", riscv_online_cpu, riscv_offline_cpu); -#endif cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", riscv_online_cpu_vec, NULL); |